{"total":30,"rows":[{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"area":"agents"},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2602.08146","title":"Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation","created":"2026-02-08","cited_by_count":7,"area":"agents"},{"id":"2602.00409","title":"Are Coding Agents Generating Over-Mocked Tests? An Empirical Study","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"id":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","cited_by_count":5,"area":"agents"},{"id":"2601.03556","title":"Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests","created":"2026-01-07","cited_by_count":4,"area":"agents"},{"id":"2511.16383","title":"An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models","created":"2025-11-20","cited_by_count":3,"area":"agents"},{"id":"2504.08113","title":"Test Amplification for REST APIs via Single and Multi-Agent LLM Systems","created":"2025-04-10","cited_by_count":1,"area":"agents"},{"id":"2505.12006","title":"SOCIA-$\\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-05-17","cited_by_count":1,"area":"agents"},{"id":"2601.12146","title":"From LLMs to Agents in Programming: The Impact of Providing an LLM with a Compiler","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2606.15828","title":"Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents","created":"2026-06-14","cited_by_count":1,"area":"agents"},{"id":"2607.08983","title":"SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2609.04681","title":"Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2509.15366","title":"Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2510.18551","title":"SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2510.27417","title":"Agentic LLMs for REST API Test Amplification: A Comparative Study Across Cloud Applications","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2511.04153","title":"BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2512.01010","title":"Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis","created":"2025-11-30","cited_by_count":0,"area":"agents"},{"id":"2604.01442","title":"Fuzzing with Agents? Generators Are All You Need","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.14590","title":"AgileLog: A Forkable Shared Log for Agents on Data Streams","created":"2026-04-16","cited_by_count":0,"area":"agents"},{"id":"2605.01471","title":"Practical Limits of Autonomous Test Repair: A Multi-Agent Case Study with LLM-Driven Discovery and Self-Correction","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2607.18057","title":"Test Coverage Analysis of Agentic Pull Requests","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.21832","title":"How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests","created":"2026-07-23","cited_by_count":0,"area":"agents"},{"id":"2607.28271","title":"Agentic Method for Deterministic Validation of Legacy Code Migration","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}